© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 2155
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    48.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    high-frequency keywords or functions commonly found in programming or technical documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    pyvene/gemma-reft-r1-9b-it-res/l20
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.55
    ChildScrollView
    -0.44
    Brainz
    -0.41
    Personendaten
    -0.40
    reszcie
    -0.40
     AssemblyCulture
    -0.38
    AddTagHelper
    -0.37
    ViewStyle
    -0.36
     MainAxisSize
    -0.35
    MemoryWarning
    -0.35
    POSITIVE LOGITS
     Qui
    0.52
     NAC
    0.52
    conditions
    0.51
     nac
    0.50
    Conditions
    0.48
     Petron
    0.48
    preuves
    0.47
    Qui
    0.46
     Karol
    0.46
    Pä
    0.46
    Activations Density 0.021%

    No Known Activations